FitMyLLM
AMD· GCN 1.0

AMD Radeon R7 M265

Running LLMs on the Radeon R7 M265 — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
2 GB
BUDGET
BANDWIDTH
29
GB/S
MODELS Q4
47/449
10%
7B Q4 SPEED
~4
SLOW
▸ MODEL COVERAGE @ Q410% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
1.7GB NEEDED
7B
3.9GB NEEDED
14B
7.9GB NEEDED
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS
▸ SPECIFICATIONS
VRAM
2 GB
BANDWIDTH
29 GB/s
FP16 COMPUTE
0.6 TFLOPS
TDP
75W
MEMORY
DDR3
ARCHITECTURE
GCN 1.0
STREAM PROCESSORS
384
COMPUTE UNITS
6
PCIE
Gen 3 x8
26
FAST MODELS · >30 TOK/S
Real-time chat speed
47
USABLE · >10 TOK/S
Comfortable for all tasks
47
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Radeon R7 M265 (or anything bigger) without committing. Pay by the second, cancel anytime.

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 47
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
286
TOK/S · 27% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
191
TOK/S · 29% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
184
TOK/S · 29% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
184
TOK/S · 29% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
101
TOK/S · 32% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
95
TOK/S · 33% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
85
TOK/S · 34% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
77
TOK/S · 35% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
77
TOK/S · 35% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
77
TOK/S · 35% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
74
TOK/S · 35% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
72
TOK/S · 35% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
68
TOK/S · 36% VRAM
A
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
52
TOK/S · 40% VRAM
A
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
52
TOK/S · 40% VRAM
A
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
50
TOK/S · 40% VRAM
A
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
45
TOK/S · 42% VRAM
A
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
45
TOK/S · 42% VRAM
A
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
43
TOK/S · 43% VRAM
A
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
43
TOK/S · 43% VRAM
A
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
43
TOK/S · 43% VRAM
A
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
42
TOK/S · 43% VRAM
B
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
35
TOK/S · 47% VRAM
B
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
34
TOK/S · 47% VRAM
B
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
32
TOK/S · 49% VRAM
B
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
30
TOK/S · 51% VRAM
B
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
27
TOK/S · 53% VRAM
C
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
24
TOK/S · 57% VRAM
C
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
23
TOK/S · 58% VRAM
C
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
21
TOK/S · 61% VRAM
C
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
21
TOK/S · 61% VRAM
C
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
21
TOK/S · 61% VRAM
C
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
21
TOK/S · 61% VRAM
C
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
20
TOK/S · 64% VRAM
C
OPT 1.3B1.3B
OPT·2K CTX· CHAT
20
TOK/S · 64% VRAM
C
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
20
TOK/S · 64% VRAM
C
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
19
TOK/S · 66% VRAM
C
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
18
TOK/S · 68% VRAM
C
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
18
TOK/S · 68% VRAM
C
Falcon-H1 1.5B1.55B
FALCON·128K CTX· CHAT· CODING
17
TOK/S · 72% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon R7 M265.

WHAT THIS CARD IS WORTH

Radeon R7 M265 holds 47 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Moondream2 1.9B at Q4_K_M.

TOKENS/SEC PER $100
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
what memory costs on this card
THE BIGGEST IT TAKES
Moondream2 1.9B1.9B · Q4_K_M1.7 GB9 tok/sEST
Falcon3-1B1.67B · Q5_K_M1.8 GB9 tok/sEST
LFM2-VL 1.6B1.6B · Q5_K_M1.7 GB9 tok/sEST
Falcon-H1 1.5B1.55B · Q6_K1.7 GB8 tok/sEST
Qwen2.5-Coder-1.5B1.5B · Q6_K1.6 GB8 tok/sEST
Qwen2 Math 1.5B1.5B · Q6_K1.6 GB8 tok/sEST
Qwen 2.5 1.5B1.5B · Q6_K1.6 GB8 tok/sEST
Stella en 1.5B v51.5B · Q6_K1.6 GB8 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M2 (8GB)5 GB$5992.8 tok/s per $100
M3 (8GB)5 GB$5992.8 tok/s per $100
M1 (8GB)5 GB$4992.2 tok/s per $100
RTX 2060 6GB6 GB$15026.7 tok/s per $100
Radeon R7 M2652 GB

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

AMD Radeon R7 M265 — 2 GB VRAM.

RADEON R7 M265 SPEC
BRAND
AMD
VRAM
2 GB DDR3
BANDWIDTH
29 GB/s
FP16 COMPUTE
0.6 TFLOPS
FP32 COMPUTE
0.6 TFLOPS
STREAM PROCESSORS
384
TDP
75 W
ARCHITECTURE
GCN 1.0
▸ AI CAPABILITY
47/ 449 models @ Q4

With 2 GB VRAM and 29 GB/s bandwidth, this GPU handles models up to 1.61B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~3 tok/s.

§ 01TOP MODELS FOR RADEON R7 M265
47 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
GPT-2 XL 1.5B1.61B1.5 GB165.1
stablelm-2-1_6b1.6B1.5 GB169.5
Falcon-H1 1.5B1.55B1.4 GB1743.8
Qwen2.5-Coder-1.5B1.5B1.4 GB1719.6
Qwen2 Math 1.5B1.5B1.4 GB1719.6
Qwen 2.5 1.5B1.5B1.4 GB1730.2
Yi Coder 1.5B1.5B1.4 GB1714.6
Stella en 1.5B v51.5B1.4 GB17
Phi-1 1.3B1.42B1.4 GB187.2
Phi-1.5 1.3B1.42B1.4 GB187.2
DeepSeek Coder 1.3B1.35B1.3 GB1916.8
EXAONE-4.0-1.2B1.3B1.3 GB2018.9
OPT 1.3B1.3B1.3 GB205.3
MiniCPM-V 4.61.3B1.3 GB2021.5
LFM2.5-1.2B-Thinking1.2B1.2 GB2119.6
Llama-3.2-1B1.2B1.2 GB2110.1
LFM2 1.2B1.2B1.2 GB2115.6
Zamba2 1.2B1.2B1.2 GB2141.5
TinyLlama 1.1B1.1B1.2 GB2313.6
MiniCPM5 1B1.08B1.1 GB2426.5