GPU OBJECT :: amd-radeon-rx-7900-xtx-24gb
Radeon RX 7900 XTX 24GB
Evidence-first hardware detail for local AI.Evidenzbasierte Hardware-Detailseite für Local AI.
FAST MEMORY
BANDWIDTH
OBSERVATION
DIRECT ANSWER
Radeon RX 7900 XTX 24GB provides 24 GB of fast memory, 960 GB/s of memory bandwidth, and reaches at least minimum memory fit for 7 of 9 currently listed BrunoSan models. Its known software path includes ROCm, HIP, PyTorch, llama.cpp. BrunoSan publishes tokens/s only with model- and runtime-specific benchmark evidence.
01 · HARDWARE
Technical data
Canonical GPU facts. Board-specific differences stay in variant evidence.
| Fast memory / VRAM | 24 GB | VERIFIED_SPEC |
|---|---|---|
| Memory type | GDDR6 | VERIFIED_SPEC |
| Memory bus | 384 bit | SOURCE_OBSERVED |
| Memory bandwidth | 960 GB/s | VERIFIED_SPEC |
| Interface | PCI Express 4.0 | SOURCE_OBSERVED |
| Board power | 355 W | VERIFIED_SPEC |
| Recommended PSU | 800 W | VERIFIED_SPEC |
| Stream processors | 6 144 | SOURCE_OBSERVED |
| Graphics processor | Radeon RX 7900 XTX | SOURCE_OBSERVED |
| Processor family | AMD | SOURCE_OBSERVED |
02 · MARKET
Current market
Observed price
Buying guidance
Strong memory fit for Qwen3-Coder-30B-A3B, Qwen3-30B-A3B, Qwen3.5-35B-A3B and more. The listed configuration carries a 800 W minimum PSU recommendation.
03 · VARIANTS
Observed board variants
Dimensions, connectors and outputs stay variant-scoped.
| Variant | GTIN | PCIe | PSU | Power | Dimensions | Display |
|---|---|---|---|---|---|---|
| GIGABYTEGV-R79XTXGAMING OC-24GD | 4719331312626 | PCI Express 4.0 | 850 W | 2x 8-pin | 331 × 50 × 138 mm | DP 2 · HDMI 2 |
04 · LOCAL AI FIT
Which BrunoSan models fit?
Exact BrunoSan model profiles, not generic 7B/14B buckets. Memory fit does not claim maximum context or runtime compatibility.
| Model | Memory target | Fit | Context |
|---|---|---|---|
| GLM-4.7-Flash | 18–24 GB | Recommended fit | Context/KV cache unbenchmarked |
| Nemotron 3.5 Lightning 30B-A3B | 20–24 GB | Recommended fit | Context/KV cache unbenchmarked |
| Qwen3-30B-A3B | 20–24 GB | Recommended fit | Context/KV cache unbenchmarked |
| Qwen3-Coder-30B-A3B | 20–24 GB | Recommended fit | Context/KV cache unbenchmarked |
| Qwen3.5-35B-A3B | 20–24 GB | Recommended fit | Context/KV cache unbenchmarked |
| Qwen3.8-27B | 18–24 GB | Recommended fit | Context/KV cache unbenchmarked |
| gpt-oss-20b | 16–24 GB | Recommended fit | Context/KV cache unbenchmarked |
| Qwen3-Coder-Next 80B-A3B | 48–64 GB | Does not fit fast memory | Context/KV cache unbenchmarked |
| gpt-oss-120b | 64–96 GB | Does not fit fast memory | Context/KV cache unbenchmarked |
05 · PERFORMANCE
Evidence before speed claims
Memory bandwidth: 960 GB/s
No model/runtime-specific benchmark is registered. No tokens/s number is published.
06 · SOFTWARE
Runtime path
ROCm/HIP path. Support varies by operating system, GPU generation and runtime; verify the exact stack before purchase.
OS: windows · linux
07 · PROS
Strengths
- 24 GB of fast memory
- 960 GB/s evidenced memory bandwidth
- Recommended-memory fit for 7 BrunoSan model profiles
- Documented software path: ROCm, HIP, PyTorch
08 · CONS
Limits
- Fast memory is insufficient for 2 larger model profiles
- No model/runtime-specific benchmark in the BrunoSan registry yet
09 · COMPARE
Nearby hardware choices
Related by memory capacity first; never a hidden performance ranking.
10 · SOURCES
Provenance
Every displayed fact keeps its evidence scope. Curated SSOT wins over source observations; board-specific Icecat fields are not silently generalized to a GPU family.
- FULL_ONLY · RX 7900 XTX Pulse · next: VENDOR_OFFICIAL
- FULL_ONLY · RX 7900 XTX Nitro+ · next: VENDOR_OFFICIAL
- FULL_ONLY · RX 7900 XTX Red Devil · next: VENDOR_OFFICIAL
- FULL_ONLY · RX 7900 XTX Taichi · next: VENDOR_OFFICIAL
Icecat source observations are provided AS IS and are not used for AI training by BrunoSan.
Icecat.biz → · AS IS disclaimer →DIREKTE ANTWORT
Radeon RX 7900 XTX 24GB bietet 24 GB schnellen Speicher, 960 GB/s Speicherbandbreite, und erreicht bei 7 von 9 aktuell gelisteten BrunoSan-Modellen mindestens den Speicher-Minimum-Fit. Der bekannte Software-Pfad umfasst ROCm, HIP, PyTorch, llama.cpp. Token/s werden nur bei einem modell- und runtime-spezifischen Benchmark veröffentlicht.
01 · HARDWARE
Technische Daten
Kanonische GPU-Fakten. Board-spezifische Unterschiede bleiben Varianten-Evidenz.
| Schneller Speicher / VRAM | 24 GB | VERIFIED_SPEC |
|---|---|---|
| Speichertyp | GDDR6 | VERIFIED_SPEC |
| Speicherbus | 384 bit | SOURCE_OBSERVED |
| Speicherbandbreite | 960 GB/s | VERIFIED_SPEC |
| Interface | PCI Express 4.0 | SOURCE_OBSERVED |
| Board Power | 355 W | VERIFIED_SPEC |
| Netzteil-Empfehlung | 800 W | VERIFIED_SPEC |
| Stream-Prozessoren | 6 144 | SOURCE_OBSERVED |
| Grafikprozessor | Radeon RX 7900 XTX | SOURCE_OBSERVED |
| Prozessorfamilie | AMD | SOURCE_OBSERVED |
02 · MARKET
Aktueller Markt
Beobachteter Preis
Kaufberatung
Starker Speicher-Fit für Qwen3-Coder-30B-A3B, Qwen3-30B-A3B, Qwen3.5-35B-A3B und weitere. Für die gelistete Konfiguration sind mindestens 800 W Netzteil-Empfehlung hinterlegt.
03 · VARIANTS
Beobachtete Board-Varianten
Abmessungen, Stromanschlüsse und Ausgänge bleiben variantenbezogen.
| Variant | GTIN | PCIe | PSU | Power | Maße | Display |
|---|---|---|---|---|---|---|
| GIGABYTEGV-R79XTXGAMING OC-24GD | 4719331312626 | PCI Express 4.0 | 850 W | 2x 8-pin | 331 × 50 × 138 mm | DP 2 · HDMI 2 |
04 · LOCAL AI FIT
Welche BrunoSan-Modelle passen?
Konkrete BrunoSan-Modellprofile statt grober 7B/14B-Klassen. Speicher-Fit behauptet weder maximales Kontextfenster noch Runtime-Kompatibilität.
| Model | Speicherziel | Fit | Context |
|---|---|---|---|
| GLM-4.7-Flash | 18–24 GB | Empfohlener Fit | Kontext/KV-Cache nicht benchmarked |
| Nemotron 3.5 Lightning 30B-A3B | 20–24 GB | Empfohlener Fit | Kontext/KV-Cache nicht benchmarked |
| Qwen3-30B-A3B | 20–24 GB | Empfohlener Fit | Kontext/KV-Cache nicht benchmarked |
| Qwen3-Coder-30B-A3B | 20–24 GB | Empfohlener Fit | Kontext/KV-Cache nicht benchmarked |
| Qwen3.5-35B-A3B | 20–24 GB | Empfohlener Fit | Kontext/KV-Cache nicht benchmarked |
| Qwen3.8-27B | 18–24 GB | Empfohlener Fit | Kontext/KV-Cache nicht benchmarked |
| gpt-oss-20b | 16–24 GB | Empfohlener Fit | Kontext/KV-Cache nicht benchmarked |
| Qwen3-Coder-Next 80B-A3B | 48–64 GB | Schneller Speicher reicht nicht | Kontext/KV-Cache nicht benchmarked |
| gpt-oss-120b | 64–96 GB | Schneller Speicher reicht nicht | Kontext/KV-Cache nicht benchmarked |
05 · PERFORMANCE
Evidenz vor Speed-Behauptung
Memory bandwidth: 960 GB/s
Kein modell-/runtime-spezifischer Benchmark registriert. Es wird keine Token/s-Zahl veröffentlicht.
06 · SOFTWARE
Runtime-Pfad
ROCm-/HIP-Pfad. Support variiert nach Betriebssystem, GPU-Generation und Runtime; den konkreten Stack vor dem Kauf prüfen.
OS: windows · linux
07 · PROS
Vorteile
- 24 GB schneller Speicher
- 960 GB/s belegte Speicherbandbreite
- Empfohlener Speicher-Fit für 7 BrunoSan-Modellprofile
- Dokumentierter Software-Pfad: ROCm, HIP, PyTorch
08 · CONS
Nachteile / Grenzen
- Für 2 größere Modellprofile reicht der schnelle Speicher nicht
- Noch kein modell-/runtime-spezifischer Benchmark im BrunoSan-Register
09 · COMPARE
Naheliegende Alternativen
Primär nach Speicherkapazität verwandt; niemals ein verstecktes Performance-Ranking.
10 · SOURCES
Provenienz
Jeder angezeigte Fakt behält seinen Evidenz-Scope. Die kuratierte SSOT hat Vorrang vor Source Observations; board-spezifische Icecat-Felder werden nicht still auf eine GPU-Familie verallgemeinert.
- FULL_ONLY · RX 7900 XTX Pulse · next: VENDOR_OFFICIAL
- FULL_ONLY · RX 7900 XTX Nitro+ · next: VENDOR_OFFICIAL
- FULL_ONLY · RX 7900 XTX Red Devil · next: VENDOR_OFFICIAL
- FULL_ONLY · RX 7900 XTX Taichi · next: VENDOR_OFFICIAL
Icecat source observations are provided AS IS and are not used for AI training by BrunoSan.
Icecat.biz → · AS IS disclaimer →